Skip to content

Conversation

@MaxenceGollier
Copy link
Collaborator

No description provided.

Copy link
Member

@dpo dpo left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Voici une 1e ronde de commentaire.

SVP nous dire combien il y a de mots.

@MaxenceGollier
Copy link
Collaborator Author

@dpo I added a workflow, we have 1096 words currently.


- **SVM with $\ell^{1/2}$ penalty:** **R2N** is the fastest, requiring the fewest gradient evaluations compared to all the other solvers.
**R2N** is the fastest, requiring the fewest gradient evaluations.
However, it requires more proximal evaluations, but these are inexpensive.
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Il me semble qu'il y a un bug quelque part car le nombre de prox diffère d'un ordre de grandeur !

@MaxenceGollier MaxenceGollier merged commit 470f236 into JuliaSmoothOptimizers:paper Oct 21, 2025
2 checks passed
@MaxenceGollier MaxenceGollier deleted the fix-pre-review-paper branch October 21, 2025 17:36
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants